INDEX

Explanations

sensitivity

New Auto-Interp

Configuration

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sensitivity

-2.02

 Sensitivity

-1.70

sensitivity

-1.69

Sensitivity

-1.49

 sensitivities

-1.31

 sensibilité

-1.22

 sensibilidad

-1.20

 sensibility

-0.89

ensitivity

-0.84

Personensuche

-0.81

POSITIVE LOGITS

à

0.50

wet

0.48

atal

0.48

IBOutlet

0.47

GetComponent

0.46

nom

0.45

 CURIAM

0.45

ics

0.45

 domain

0.45

tici

0.45

Activations Density 0.058%